Cerebral small vessel disease (CSVD) visible on MRI can be asymptomatic. We sought to develop and validate a model for detecting CSVD in rural older adults.
This study included 1,192 participants in the MRI sub-study within the Multidomain Interventions to Delay Dementia and Disability in Rural China. Total sample was randomly divided into training set and validation set. MRI markers of CSVD were assessed following the international criteria, and total CSVD burden was assessed on a scale from 0 to 4. Logistic regression analyses were used to screen risk factors and develop the diagnostic model. A nomogram was used to visualize the model. Model performance was assessed using the area under the receiver-operating characteristic curve (AUC), calibration plot, and decision curve analysis.
The model included age, high blood pressure, white blood cell count, neutrophil-to-lymphocyte ratio (NLR), and history of cerebral infarction. The AUC was 0.71 (95% CI, 0.67–0.76) in the training set and 0.69 (95% CI, 0.63–0.76) in the validation set. The model showed high coherence between predicted and observed probabilities in both the training and validation sets. The model had higher net benefits than the strategy assuming all participants either at high risk or low risk of CSVD for probability thresholds ranging 50–90% in the training set, and 65–98% in the validation set.
A model that integrates routine clinical factors could detect CSVD in older adults, with good discrimination and calibration. The model has implication for clinical decision-making.